AoiZora: Compiler-Agnostic, Placement-Aware Auto-Parallelization for Video Diffusion Transformers
cs.DC, cs.LG
Submitted: 2026-06-16
Updated: 2026-10-31
Code: https://github.com/ax-ml/jax
Terminology
Sources
- CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- Wan: Open and Advanced Large-Scale Video Generative Models
- Latte: Latent Diffusion Transformer for Video Generation
- Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
- DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale
- SwiftFusion: Scalable Sequence Parallelism for Distributed Inference of Diffusion Transformers on GPUs
- xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
- TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings
- GSPMD: General and Scalable Parallelization for ML Computation Graphs
- GENSERVE: Efficient Co-Serving of Heterogeneous Diffusion Model Workloads
- Beyond Data and Model Parallelism for Deep Neural Networks
Related papers
- Programmable Probabilistic Computer with 1,000,000 p-bits
- BatchGen: An Architecture for Scalable and Efficient Batch Inference
- Seamless Reconfiguration for DAG-BFT (Technical Report)
- ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
- iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
- TIRx: A Unified Tile Primitive ML Compiler Across Heterogeneous Backends